Chinese traditional sculpture art has a relatively long history, and it is also relatively famous all over the world. Chinese traditional sculpture art is not only a display of painting techniques and carving techniques, it also has the function of preserving Chinese history and culture. The traditional engraving technology will use the basic theory of drawing to design related factors. However, this kind of carving art is more cost-intensive and human and material resources. Computer-aided technology can assist CAD technology to reconstruct traditional Chinese sculptures. However, it is also difficult for traditional CAD reconstruction techniques to take into account the cultural information, shape information and time correlation of traditional Chinese sculptures. This research uses MPCNN and LSTM technology in artificial intelligence algorithm to assist computer-aided technology and CAD technology to realize the 3D reconstruction task of traditional Chinese sculpture. The research results found that this artificial intelligence theoryassisted CAD reconstruction technology can intuitively restore the pattern information, shape information and cultural information of traditional Chinese sculptures, which is mainly due to the fact that MPCNN-LSTM technology can accurately mine and evaluate the relevant characteristics of traditional Chinese sculptures.

The environment for training and recognition in Chinese speech recognition under computer-aided design may vary due to the difference of channel and background noise. When the trained model cannot well represent the test data, the recognition rate of the system will drop sharply. The computer-aided design method focuses on using a small amount of Chinese voice data to improve the performance of the system in the test environment. In this paper, we choose the BiLSTM CRF word separation model under deep learning as the improved benchmark model, and combine the Bert language pre-training module to enhance the performance of Chinese word separation. Combining the deep learning sample transfer learning theory and the improved sampling strategy, an adaptive translation model for intelligent Chinese domain is constructed. The experimental results show that Bert Chinese word segmentation model is superior to other word segmentation models in different data sets and has the best word segmentation performance, which can provide reliable support for the application experiment of this model. The test results show that this method can achieve high speech recognition accuracy and good application results.

Urban square landscape construction has important value in urban development, environmental protection, aesthetic appreciation and so on. The introduction of computer aided technology to promote the digital transformation of landscape planning and design can further improve the efficiency and quality of planning and design. The urban square landscape design and planning project is taken as the main body of the study. Specific design and analysis were carried out for the experimental platform construction, three-dimensional object realization and urban square landscape design model construction scheme, and AHP was used to establish a virtual reality urban square landscape design evaluation model. The final evaluation results show that using computer technology and software can complete the construction of virtual reality scene with high efficiency, accuracy and quality. Based on the evaluation model of city square landscape design and integration of CAD rendering technology, the three-dimensional city square landscape design simulation system designed in this paper closely integrates. production of domestic plant database, suitable for city square landscape terrain design, parametric design of city square ancillary facilities, etc., well meet the needs of professional designers, fully fill the blank of domestic city square professional software.